src/test/utf8.c

   1 /*****************************************************************************
   2  * utf8.c: Test for UTF-8 encoding/decoding stuff
   3  *****************************************************************************
   4  * Copyright (C) 2006 Rémi Denis-Courmont
   5  * $Id$
   6  *
   7  * This program is free software; you can redistribute it and/or modify
   8  * it under the terms of the GNU General Public License as published by
   9  * the Free Software Foundation; either version 2 of the License, or
  10  * (at your option) any later version.
  11  *
  12  * This program is distributed in the hope that it will be useful,
  13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15  * GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License
  18  * along with this program; if not, write to the Free Software
  19  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston MA 02110-1301, USA.
  20  *****************************************************************************/
  21
  22 #ifdef HAVE_CONFIG_H
  23 # include "config.h"
  24 #endif
  25
  26 #include <vlc_common.h>
  27 #include <vlc_charset.h>
  28
  29 #include <stdio.h>
  30 #include <stdlib.h>
  31 #include <stdbool.h>
  32
  33 static void test (const char *in, const char *out)
  34 {
  35     bool isutf8 = !strcmp (in, out);
  36     char *str = strdup (in);
  37     if (str == NULL)
  38         abort ();
  39
  40     if (isutf8)
  41         printf ("\"%s\" should be accepted...\n", in);
  42     else
  43         printf ("\"%s\" should be rewritten as \"%s\"...\n", in, out);
  44
  45     if ((IsUTF8 (in) != NULL) != isutf8)
  46     {
  47         printf (" ERROR: IsUTF8 (%s) failed\n", in);
  48         exit (1);
  49     }
  50
  51     if ((EnsureUTF8 (str) != NULL) != isutf8)
  52     {
  53         printf (" ERROR: EnsureUTF8 (%s) failed\n", in);
  54         exit (2);
  55     }
  56
  57     if (strcmp (str, out))
  58     {
  59         printf (" ERROR: got \"%s\"\n", str);
  60         exit (3);
  61     }
  62
  63     if ((EnsureUTF8 (str) == NULL) || IsUTF8 (str) == NULL)
  64     {
  65         printf (" ERROR: EnsureUTF8 (%s) is not UTF-8\n", in);
  66         exit (4);
  67     }
  68     free (str);
  69 }
  70
  71 static void test_strcasestr (const char *h, const char *n, ssize_t offset)
  72 {
  73     printf ("\"%s\" should %sbe found in \"%s\"...\n", n,
  74             (offset != -1) ? "" : "not ", h);
  75
  76     const char *ret = vlc_strcasestr (h, n);
  77     if (offset == -1)
  78     {
  79         if (ret != NULL)
  80         {
  81             printf ("ERROR: got \"%s\"\n", ret);
  82             exit (10);
  83         }
  84     }
  85     else
  86     {
  87         if (ret == NULL)
  88         {
  89             printf ("ERROR: not found\n");
  90             exit (11);
  91         }
  92         if ((ret - h) != offset)
  93         {
  94             printf ("ERROR: got \"%s\" instead of \"%s\"\n",
  95                     ret, h + offset);
  96             exit (12);
  97         }
  98     }
  99 }
 100
 101
 102 int main (void)
 103 {
 104     (void)setvbuf (stdout, NULL, _IONBF, 0);
 105     test ("", "");
 106
 107     test ("this_should_not_be_modified_1234",
 108           "this_should_not_be_modified_1234");
 109
 110     test ("\xFF", "?"); // invalid byte
 111     test ("\xEF\xBB\xBFHello", "\xEF\xBB\xBFHello"); // BOM
 112     test ("\x00\xE9", ""); // no conversion past end of string
 113
 114     test ("T\xC3\xA9l\xC3\xA9vision \xE2\x82\xAC", "Télévision €");
 115     test ("T\xE9l\xE9vision", "T?l?vision");
 116     test ("\xC1\x94\xC3\xa9l\xC3\xA9vision", "??élévision"); /* overlong */
 117
 118     test ("Hel\xF0\x83\x85\x87lo", "Hel????lo"); /* more overlong */
 119
 120     test_strcasestr ("", "", 0);
 121     test_strcasestr ("", "a", -1);
 122     test_strcasestr ("a", "", 0);
 123     test_strcasestr ("heLLo", "l", 2);
 124     test_strcasestr ("heLLo", "lo", 3);
 125     test_strcasestr ("heLLo", "llo", 2);
 126     test_strcasestr ("heLLo", "la", -1);
 127     test_strcasestr ("heLLo", "oa", -1);
 128     test_strcasestr ("Télé", "é", 1);
 129     test_strcasestr ("Télé", "élé", 1);
 130     test_strcasestr ("Télé", "léé", -1);
 131
 132     return 0;
 133 }